Optimize a few modes for hashcat_tuning.hctab for budget NV cards

[hashcat.git] / OpenCL / m12000.cl

diff --git a/OpenCL/m12000.cl b/OpenCL/m12000.cl
index d85fbf4..00b0aac 100644 (file)
--- a/OpenCL/m12000.cl
+++ b/OpenCL/m12000.cl
@@ -15,14 +15,13 @@
 
 #include "include/kernel_functions.c"
 
-#include "types_ocl.c"
-#include "common.c"
+#include "OpenCL/types_ocl.c"
+#include "OpenCL/common.c"
 
-#ifdef  VECT_SIZE1
-#define COMPARE_M "check_multi_vect1_comp4.c"
-#endif
+#define COMPARE_S "OpenCL/check_single_comp4.c"
+#define COMPARE_M "OpenCL/check_multi_comp4.c"
 
-static void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
+void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
 {
   u32 A = digest[0];
   u32 B = digest[1];
@@ -150,7 +149,7 @@ static void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], c
   digest[4] += E;
 }
 
-static void hmac_sha1_pad (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5])
+void hmac_sha1_pad (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5])
 {
   w0[0] = w0[0] ^ 0x36363636;
   w0[1] = w0[1] ^ 0x36363636;
@@ -203,7 +202,7 @@ static void hmac_sha1_pad (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[
   sha1_transform (w0, w1, w2, w3, opad);
 }
 
-static void hmac_sha1_run (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5], u32 digest[5])
+void hmac_sha1_run (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5], u32 digest[5])
 {
   digest[0] = ipad[0];
   digest[1] = ipad[1];
@@ -239,7 +238,7 @@ static void hmac_sha1_run (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[
   sha1_transform (w0, w1, w2, w3, digest);
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12000_init (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global pbkdf2_sha1_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pbkdf2_sha1_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m12000_init (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global pbkdf2_sha1_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pbkdf2_sha1_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
 {
   /**
    * base
@@ -251,31 +250,31 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12000_init (__gl
 
   u32 w0[4];
 
-  w0[0] = swap_workaround (pws[gid].i[ 0]);
-  w0[1] = swap_workaround (pws[gid].i[ 1]);
-  w0[2] = swap_workaround (pws[gid].i[ 2]);
-  w0[3] = swap_workaround (pws[gid].i[ 3]);
+  w0[0] = swap32 (pws[gid].i[ 0]);
+  w0[1] = swap32 (pws[gid].i[ 1]);
+  w0[2] = swap32 (pws[gid].i[ 2]);
+  w0[3] = swap32 (pws[gid].i[ 3]);
 
   u32 w1[4];
 
-  w1[0] = swap_workaround (pws[gid].i[ 4]);
-  w1[1] = swap_workaround (pws[gid].i[ 5]);
-  w1[2] = swap_workaround (pws[gid].i[ 6]);
-  w1[3] = swap_workaround (pws[gid].i[ 7]);
+  w1[0] = swap32 (pws[gid].i[ 4]);
+  w1[1] = swap32 (pws[gid].i[ 5]);
+  w1[2] = swap32 (pws[gid].i[ 6]);
+  w1[3] = swap32 (pws[gid].i[ 7]);
 
   u32 w2[4];
 
-  w2[0] = swap_workaround (pws[gid].i[ 8]);
-  w2[1] = swap_workaround (pws[gid].i[ 9]);
-  w2[2] = swap_workaround (pws[gid].i[10]);
-  w2[3] = swap_workaround (pws[gid].i[11]);
+  w2[0] = swap32 (pws[gid].i[ 8]);
+  w2[1] = swap32 (pws[gid].i[ 9]);
+  w2[2] = swap32 (pws[gid].i[10]);
+  w2[3] = swap32 (pws[gid].i[11]);
 
   u32 w3[4];
 
-  w3[0] = swap_workaround (pws[gid].i[12]);
-  w3[1] = swap_workaround (pws[gid].i[13]);
-  w3[2] = swap_workaround (pws[gid].i[14]);
-  w3[3] = swap_workaround (pws[gid].i[15]);
+  w3[0] = swap32 (pws[gid].i[12]);
+  w3[1] = swap32 (pws[gid].i[13]);
+  w3[2] = swap32 (pws[gid].i[14]);
+  w3[3] = swap32 (pws[gid].i[15]);
 
   /**
    * salt
@@ -288,20 +287,20 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12000_init (__gl
   u32 esalt_buf2[4];
   u32 esalt_buf3[4];
 
-  esalt_buf0[0] = swap_workaround (esalt_bufs[salt_pos].salt_buf[ 0]);
-  esalt_buf0[1] = swap_workaround (esalt_bufs[salt_pos].salt_buf[ 1]);
-  esalt_buf0[2] = swap_workaround (esalt_bufs[salt_pos].salt_buf[ 2]);
-  esalt_buf0[3] = swap_workaround (esalt_bufs[salt_pos].salt_buf[ 3]);
-  esalt_buf1[0] = swap_workaround (esalt_bufs[salt_pos].salt_buf[ 4]);
-  esalt_buf1[1] = swap_workaround (esalt_bufs[salt_pos].salt_buf[ 5]);
-  esalt_buf1[2] = swap_workaround (esalt_bufs[salt_pos].salt_buf[ 6]);
-  esalt_buf1[3] = swap_workaround (esalt_bufs[salt_pos].salt_buf[ 7]);
-  esalt_buf2[0] = swap_workaround (esalt_bufs[salt_pos].salt_buf[ 8]);
-  esalt_buf2[1] = swap_workaround (esalt_bufs[salt_pos].salt_buf[ 9]);
-  esalt_buf2[2] = swap_workaround (esalt_bufs[salt_pos].salt_buf[10]);
-  esalt_buf2[3] = swap_workaround (esalt_bufs[salt_pos].salt_buf[11]);
-  esalt_buf3[0] = swap_workaround (esalt_bufs[salt_pos].salt_buf[12]);
-  esalt_buf3[1] = swap_workaround (esalt_bufs[salt_pos].salt_buf[13]);
+  esalt_buf0[0] = swap32 (esalt_bufs[salt_pos].salt_buf[ 0]);
+  esalt_buf0[1] = swap32 (esalt_bufs[salt_pos].salt_buf[ 1]);
+  esalt_buf0[2] = swap32 (esalt_bufs[salt_pos].salt_buf[ 2]);
+  esalt_buf0[3] = swap32 (esalt_bufs[salt_pos].salt_buf[ 3]);
+  esalt_buf1[0] = swap32 (esalt_bufs[salt_pos].salt_buf[ 4]);
+  esalt_buf1[1] = swap32 (esalt_bufs[salt_pos].salt_buf[ 5]);
+  esalt_buf1[2] = swap32 (esalt_bufs[salt_pos].salt_buf[ 6]);
+  esalt_buf1[3] = swap32 (esalt_bufs[salt_pos].salt_buf[ 7]);
+  esalt_buf2[0] = swap32 (esalt_bufs[salt_pos].salt_buf[ 8]);
+  esalt_buf2[1] = swap32 (esalt_bufs[salt_pos].salt_buf[ 9]);
+  esalt_buf2[2] = swap32 (esalt_bufs[salt_pos].salt_buf[10]);
+  esalt_buf2[3] = swap32 (esalt_bufs[salt_pos].salt_buf[11]);
+  esalt_buf3[0] = swap32 (esalt_bufs[salt_pos].salt_buf[12]);
+  esalt_buf3[1] = swap32 (esalt_bufs[salt_pos].salt_buf[13]);
   esalt_buf3[2] = 0;
   esalt_buf3[3] = (64 + salt_len + 4) * 8;
 
@@ -342,7 +341,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12000_init (__gl
   }
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12000_loop (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global pbkdf2_sha1_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pbkdf2_sha1_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m12000_loop (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global pbkdf2_sha1_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pbkdf2_sha1_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
 {
   const u32 gid = get_global_id (0);
 
@@ -429,7 +428,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12000_loop (__gl
   }
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12000_comp (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global pbkdf2_sha1_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pbkdf2_sha1_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m12000_comp (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global pbkdf2_sha1_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pbkdf2_sha1_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
 {
   /**
    * base